Agents

Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.

patelr3/agents

Agent Claude Code

Enforces architectural integrity by validating layering, module boundaries, domain rules, and separation of concerns across the codebase.

not rated 2 4mo ago A 27 tokens original MIT

bug-fix-verifier

1874

script-development/claude

Agent Claude Code

Verify that a bug fix actually resolves the defect described in BUG.md and doesn't introduce obvious regressions. Spawned by /fix-bug before PR creation as the blocking gate for bug-fix branches.

not rated 2 changed 8d ago A 47 tokens

elysia-expert

1875

CreateDer/agents

Agent Claude Code

Expert in building high-performance and type-safe applications using the ElysiaJS framework. Focused on functional patterns, end-to-end type safety, and performance optimization specific to ElysiaJS and Bun runtime.

not rated 2 2mo ago A 47 tokens

investigator

1876

21digitalai/claude-code-framework

Agent Claude Code

Use this agent to investigate complex issues, research implementations, or track down root causes while keeping the main context clean. The investigator does deep research but returns only essential findings. Examples: Context: Debugging an intermittent error. user: 'Users are getting random 401 errors but only…

not rated 2 3mo ago A 261 tokens

code-reviewer

1877

pierrefdz/claude

Agent Claude Code

Research code reviewer. Use when reviewing PyTorch/ML code to flag over-engineering and encourage simple, readable code.

not rated 2 7mo ago A 28 tokens

scope-creep-craig

1878

tiwillia/specware

Agent Claude Code

Use this agent when you need to review implementation plans or code implementations to ensure they strictly adhere to requirements without unnecessary complexity or feature additions. Examples: Context: The user has written a function to validate email addresses but added regex patterns for international domains when…

not rated 2 4mo ago A 0 tokens

prh-issue-creator

1879

MH4GF/claude-code

Agent Claude Code

An agent that creates a Linear issue for adding an English-to-Japanese replacement rule to prh.yml, a spelling and wording rules file. It passes the work to a background coding session that later edits and commits the change.

not rated 2 yesterday A 0 tokens original MIT

db-agent

1880

johanolofsson72/Claude

Agent Claude Code

Database operations specialist for SQLite and Entity Framework Core. Use for schema design, migrations, seed data, query optimization, and database troubleshooting.

not rated 2 yesterday A 30 tokens

character-creation

1881

owlot/claude-dnd-dungeon-master

Agent Claude Code

Walk the DM through character creation for all players before the first session. Asks only the questions relevant to each character's race, class, and level. Outputs a completed character file for each PC. Use when the DM says "Create characters for campaign [name]" or "Add character [name] for campaign [name]".

not rated 2 21d ago A 70 tokens

MIGRATION_SUMMARY

1882

Red3199/MoondevRED

Agent Claude Code

This document provides a complete migration plan for converting the existing command-based system (.claude/commands/) to the new intelligent agent-based system (.claude/agents/). The migration preserves all functionality while adding natural language understanding, intelligent coordination, and improved…

not rated 2 8mo ago A 0 tokens

i18n-translator

1883

solarcell1475/happy-cursor-agent

Agent Claude Code

Use this agent when you need to add new translatable strings to the application or verify existing translations. This includes: adding new UI text that needs to be translated, ensuring translations are consistent across all language files, verifying that translations fit the UI context (headers, buttons, multiline…

not rated 2 6mo ago A 0 tokens

Human-Concierge

1884

10K-Digital/claude-code-agents

Agent Claude Code

Manages human-agent interaction, processes all human requests including feature requests, bug reports, agent clarifications, and strategic decisions requiring human input or approval.

not rated 2 1y ago A 35 tokens

task-coder

1885

Xananthium/claude-code-agents

Agent Claude Code

Implements code for micro tasks. Reads research from agentcontext/tasks/TASK{N}research.md files created by task-planner. Calls Explore or research-specialist directly if additional research needed. Use this agent for all code implementation - orchestrator never codes directly.

not rated 2 6mo ago A 57 tokens

ux-reviewer

1886

balajivis/mai-class

Agent Claude Code

Use this agent when UI components, layouts, styles, or design-related code has been written or modified and needs review for Material Design compliance and dark theme best practices. Also use when the user asks for feedback on UI/UX decisions, color choices, spacing, typography, or accessibility in a dark theme…

not rated 2 4mo ago A 258 tokens

units-agent

1887

sashajdn/dotf

Agent Claude Code

Agent with git worktree unit management preloaded.

not rated 2 13d ago A 12 tokens

chief-of-staff

1888

askwigconsulting/cohort

Agent Claude Code

Triages a cross-functional request and names the right specialist(s) to consult. Use proactively when a request spans business functions.

not rated 2 1mo ago A 30 tokens original MIT

solar-graphic-designer

1889

elevarus-admin/agent-example

Agent Claude Code

The SolarFY fleet's single image engine. Produces ONE on-brand SolarFY image (isometric scene illustration OR flat data infographic, Clean Daylight palette) from a brief, end to end: craft the nano-banana prompt, generate, run the QA/QC checklist by VIEWING it, upload to WP media with alt text, and return the media id…

not rated 2 1mo ago A 0 tokens

code-reviewer

1890

cwoodruff/dotnet-claude-workshop-content

Agent Claude Code

Expert .NET code review specialist. Proactively reviews C# code for quality, architecture violations, and maintainability. Use immediately after writing or modifying code.

not rated 2 2mo ago A 35 tokens original MIT

cm-decider

1891

Aleksacom/claude-code-orchestration-agents

Agent Claude Code

Routes individual planning questions to AUTORESOLVE or ESCALATE. Used when cm-planner surfaces multiple questions and the main agent needs to decide which require human ratification vs which can be auto-resolved with the recommended option. Read-only — produces routing verdicts, not implementations.

not rated 2 4mo ago A 60 tokens original MIT

memory-searcher

1892

unclutter-pro/atlas

Agent Claude Code

Memory search and recall specialist. Use when you need to find past decisions, conversations, project history, learned workflows, or any stored knowledge from the agent's memory system. Returns structured summaries.

not rated 2 3d ago A 42 tokens original MIT

README

1893

summarybotng/summarybot-ng

Agent Claude Code

This directory contains sub-agent definitions organized by type and purpose. Each agent has specific capabilities, tool restrictions, and naming conventions that trigger automatic delegation.

not rated 2 3mo ago A 0 tokens copy · 86% MIT

agy-worker

1894

rhan1/crewline

Agent Claude Code

Executes a task on Antigravity (Gemini) instead of Claude, so the work bills to the idle agy quota rather than the Anthropic window. Use for mechanical code, codebase exploration and file-reading research, long-context reads, batch work, test generation, and first-pass drafts of artifacts ≥30 lines. Do NOT use for…

not rated 2 19d ago A 101 tokens original MIT

researcher

1895

brightbear2026/research-agent

Agent Claude Code

A research sub-agent that investigates one section of a larger research project and writes a sourced draft. It checks sources against one another and labels facts, opinions, disputes, judgments, and guesses.

not rated 2 23d ago A 62 tokens original MIT

tech-stack-researcher

1896

mj11rock/claude-code

Agent Claude Code

Use this agent when the user is planning new features or functionality and needs guidance on technology choices, architecture decisions, or implementation approaches. Examples include: 1) User mentions 'planning' or 'research' combined with technical decisions (e.g., 'I'm planning to add real-time notifications, what…

not rated 2 7mo ago A 0 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: